Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 1215
    Prev
    Next
    INDEX
    Explanations

    information related to email addresses and contact details

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    563
    +0.10
    0.5%
    136
    +0.09
    0.4%
    467
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    267
    +0.10
    0.05
    373
    +0.09
    -0.04
    136
    +0.09
    0.05
    Negative Logits
    orage
    -0.63
    anza
    -0.60
     subord
    -0.58
    cffffcc
    -0.58
    itiz
    -0.57
    ité
    -0.57
    SPONSORED
    -0.56
    reality
    -0.55
    vation
    -0.55
    ]),
    -0.55
    POSITIVE LOGITS
    <|endoftext|>
    1.03
    Advertisements
    0.87
    Featured
    0.84
     Comments
    0.80
     airs
    0.74
    Follow
    0.73
     Patreon
    0.72
     ®
    0.72
     meantime
    0.72
    Topics
    0.72
    Activations Density 0.660%

    No Known Activations